LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 2.5 Flash vs gpt-oss-120b

Updated October 21, 2026. 52 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 2.5 Flash Replace gpt-oss-120b
Gemini 2.5 FlashGoogle
Coding
28.7
Overall
15.5
Output $/M
$2.50
44
gpt-oss-120bOpenAI
Coding
34.5
Overall
11.6
Output $/M
$0.60
8
vs boards won of 52 shared

Decision reading

Pick gpt-oss-120b for coding: it scores 34.5 on the Vibe Coding Index against 28.7 for Gemini 2.5 Flash.

Pick Gemini 2.5 Flash when a solved task costs $0.466 against $0.51, or when the context window is larger, 1.05M against 131K tokens.

Model AGemini 2.5 FlashGoogle28.7/1001 independent benchmark$0.466 per solved taskModel Bgpt-oss-120bOpenAI34.5/1002 independent benchmarks$0.51 per solved task
Shared results
52
Gemini 2.5 Flash only
17
gpt-oss-120b only
26
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Gemini 2.5 Flash 28.7 from 1 benchmark, gpt-oss-120b 34.5 from 2 benchmarks.
Widest category
Agentic work, 18.8 points apart on average over 2 shared benchmarks.
Widest single gap
τ²-Bench Telecom: Gemini 2.5 Flash 31.6% against gpt-oss-120b 65.8%, 34.2 points apart on a 0 to 100 scale.
Output price
Gemini 2.5 Flash $2.50 against gpt-oss-120b $0.60 per million output tokens, 4.2x apart.
Context window
Gemini 2.5 Flash takes 1.05M tokens, gpt-oss-120b 131K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryGemini 2.5 FlashBarsgpt-oss-120bTies
Coding33
Intelligence20
Agentic work11
Reasoning51
Math22
Knowledge50
Web design60
General201
All shared boards448
CodingLike-for-likeFour of these boards feed the Vibe Coding Index33
Coding benchmarks for Gemini 2.5 Flash and gpt-oss-120b
BenchmarkGemini 2.5 Flashgpt-oss-120bLeader
Aider polyglotNot measured41.8%Only gpt-oss-120b measured
SWE-bench Verified28.7%26.0%Gemini 2.5 Flash
AA Coding IndexNot measured30.4Only gpt-oss-120b measured
LiveCodeBench (Vals AI)Not measured83.2%Only gpt-oss-120b measured
SWE-bench Verified (Vals AI)Not measured33.6%Only gpt-oss-120b measured
LiveCodeBench (Artificial Analysis run)69.5%87.8%gpt-oss-120b
SciCodeNot measured34.0%Only gpt-oss-120b measured
Terminal-Bench Hard (Artificial Analysis run)13.6%23.5%gpt-oss-120b
Terminal-Bench17.1%18.7%gpt-oss-120b
WeirdMLNot measured48.2%Only gpt-oss-120b measured
ALE-BenchNot measured575.6Only gpt-oss-120b measured
LMArena Text: coding14231379Gemini 2.5 Flash
LMArena Text: software and IT14251387Gemini 2.5 Flash
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemini 2.5 Flash and gpt-oss-120b
BenchmarkGemini 2.5 Flashgpt-oss-120bLeader
AA Intelligence Index15.511.6Gemini 2.5 Flash
Epoch Capabilities Index142.9139.8Gemini 2.5 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for Gemini 2.5 Flash and gpt-oss-120b
BenchmarkGemini 2.5 Flashgpt-oss-120bLeader
AA Agentic IndexNot measured3.7Only gpt-oss-120b measured
τ²-Bench Telecom31.6%65.8%gpt-oss-120b
APEX-AgentsNot measured4.4%Only gpt-oss-120b measured
METR time horizonsNot measured56.6%Only gpt-oss-120b measured
BALROG33.5%Not measuredOnly Gemini 2.5 Flash measured
Vending-Bench 2$549-$22Gemini 2.5 Flash
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index51
Reasoning benchmarks for Gemini 2.5 Flash and gpt-oss-120b
BenchmarkGemini 2.5 Flashgpt-oss-120bLeader
GPQA DiamondNot measured78.5%Only gpt-oss-120b measured
GPQA Diamond (Artificial Analysis run)79.0%78.2%Gemini 2.5 Flash
Humanity's Last Exam (Artificial Analysis run)12.1%19.6%gpt-oss-120b
GPQA Diamond (Epoch AI run)Not measured75.8%Only gpt-oss-120b measured
ARC-AGI33.3%Not measuredOnly Gemini 2.5 Flash measured
ARC-AGI-22.5%Not measuredOnly Gemini 2.5 Flash measured
SimpleBench41.2%22.1%Gemini 2.5 Flash
Mystery game puzzlesNot measured2.0%Only gpt-oss-120b measured
LMArena Text: hard prompts14221364Gemini 2.5 Flash
LMArena Text: expert14261356Gemini 2.5 Flash
LMArena Text: hard prompts in English14201368Gemini 2.5 Flash
LMArena Vision: diagrams1245Not measuredOnly Gemini 2.5 Flash measured
LMArena Vision: homework1244Not measuredOnly Gemini 2.5 Flash measured
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index22
Math benchmarks for Gemini 2.5 Flash and gpt-oss-120b
BenchmarkGemini 2.5 Flashgpt-oss-120bLeader
AIMENot measured92.6%Only gpt-oss-120b measured
MATH 500 (Vals AI)Not measured94.8%Only gpt-oss-120b measured
MGSM (Vals AI)Not measured92.0%Only gpt-oss-120b measured
AA Math Index73.393.4gpt-oss-120b
AIME 2025 (Artificial Analysis run)73.3%93.4%gpt-oss-120b
OTIS Mock AIMENot measured88.9%Only gpt-oss-120b measured
LMArena Text: math14111389Gemini 2.5 Flash
LMArena Text: mathematical work14221386Gemini 2.5 Flash
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for Gemini 2.5 Flash and gpt-oss-120b
BenchmarkGemini 2.5 Flashgpt-oss-120bLeader
MMLU ProNot measured79.2%Only gpt-oss-120b measured
LegalBench (Vals AI)Not measured75.9%Only gpt-oss-120b measured
CaseLaw (Vals AI)Not measured48.8%Only gpt-oss-120b measured
CorpFin (Vals AI)Not measured58.2%Only gpt-oss-120b measured
TaxEval (Vals AI)Not measured71.6%Only gpt-oss-120b measured
MedQA (Vals AI)Not measured91.4%Only gpt-oss-120b measured
MedCode (Vals AI)40.4%Not measuredOnly Gemini 2.5 Flash measured
MMLU Pro (Artificial Analysis run)83.2%80.8%Gemini 2.5 Flash
LMArena Text: science14331382Gemini 2.5 Flash
LMArena Text: medicine and healthcare14281388Gemini 2.5 Flash
LMArena Text: legal and government14301355Gemini 2.5 Flash
LMArena Text: business and finance14041359Gemini 2.5 Flash
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for Gemini 2.5 Flash and gpt-oss-120b
BenchmarkGemini 2.5 Flashgpt-oss-120bLeader
Design Arena: websites1074968Gemini 2.5 Flash
Design Arena: UI components1005927Gemini 2.5 Flash
Design Arena: game dev1005992Gemini 2.5 Flash
Design Arena: data viz1060987Gemini 2.5 Flash
Design Arena: 3D1021901Gemini 2.5 Flash
Design Arena: all code categories1059963Gemini 2.5 Flash
Design Arena: SVG1018Not measuredOnly Gemini 2.5 Flash measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index201
General benchmarks for Gemini 2.5 Flash and gpt-oss-120b
BenchmarkGemini 2.5 Flashgpt-oss-120bLeader
SAGE (Vals AI)44.8%Not measuredOnly Gemini 2.5 Flash measured
MedScribe (Vals AI)83.0%Not measuredOnly Gemini 2.5 Flash measured
IFBench50.3%69.0%gpt-oss-120b
Long context reasoning (AA-LCR)65.3%52.0%Gemini 2.5 Flash
DTBench76.5%76.3%Gemini 2.5 Flash
LMCA27.5%22.1%Gemini 2.5 Flash
Fiction.LiveBenchNot measured44.4%Only gpt-oss-120b measured
Creative writing (Lech Mazur)Not measured77.1%Only gpt-oss-120b measured
Surface Evolver BenchNot measured25.0%Only gpt-oss-120b measured
LMArena Text14171366Gemini 2.5 Flash
LMArena Text: instruction following14051318Gemini 2.5 Flash
LMArena Text: creative writing14001274Gemini 2.5 Flash
LMArena Vision1235Not measuredOnly Gemini 2.5 Flash measured
LMArena Text: English14181375Gemini 2.5 Flash
LMArena Text: non-English14091351Gemini 2.5 Flash
LMArena Text: Chinese14491385Gemini 2.5 Flash
LMArena Text: German14171353Gemini 2.5 Flash
LMArena Text: Japanese13961331Gemini 2.5 Flash
LMArena Text: Korean13851282Gemini 2.5 Flash
LMArena Text: French14321370Gemini 2.5 Flash
LMArena Text: Spanish14221389Gemini 2.5 Flash
LMArena Text: Russian14151343Gemini 2.5 Flash
LMArena Text: Polish14131353Gemini 2.5 Flash
LMArena Text: multi-turn14081340Gemini 2.5 Flash
LMArena Text: longer queries14191319Gemini 2.5 Flash
LMArena Text: writing and language14051306Gemini 2.5 Flash
LMArena Text: entertainment and media13931292Gemini 2.5 Flash
LMArena Vision: English1239Not measuredOnly Gemini 2.5 Flash measured
LMArena Vision: Chinese1284Not measuredOnly Gemini 2.5 Flash measured
LMArena Vision: reading text1237Not measuredOnly Gemini 2.5 Flash measured
LMArena Vision: humor1225Not measuredOnly Gemini 2.5 Flash measured
LMArena Vision: captioning1277Not measuredOnly Gemini 2.5 Flash measured
LMArena Vision: recognizing things1252Not measuredOnly Gemini 2.5 Flash measured
LMArena Vision: creative writing1241Not measuredOnly Gemini 2.5 Flash measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 2.5 Flash and gpt-oss-120b
BenchmarkGemini 2.5 Flashgpt-oss-120bLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Gemini 2.5 Flash$0.0015Fits in one request
gpt-oss-120b$0.0004Fits in one request

gpt-oss-120b costs less

Repository review

50K input + 3K output tokens

Gemini 2.5 Flash$0.022Fits in one request
gpt-oss-120b$0.0093Fits in one request

gpt-oss-120b costs less

Agent loop

200K input + 10K output tokens

Gemini 2.5 Flash$0.085Fits in one request
gpt-oss-120b$0.036Exceeds the context window

gpt-oss-120b costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Gemini 2.5 Flash and gpt-oss-120b
SpecificationGoogle Gemini 2.5 FlashOpenAI gpt-oss-120b
MakerGoogleOpenAI
WeightsNo public weights listedOpen weights
ReleasedJune 17, 2025August 5, 2025
Context window1.05M131K
Input $/Mtok$0.30$0.15
Output $/Mtok$2.50$0.60
Coding index28.734.5
Independent measurements behind it12
Cost per solved task$0.466$0.51
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 2.5 Flash better than gpt-oss-120b for coding?

Pick gpt-oss-120b for coding: it scores 34.5 on the Vibe Coding Index against 28.7 for Gemini 2.5 Flash. Pick Gemini 2.5 Flash when a solved task costs $0.466 against $0.51, or when the context window is larger, 1.05M against 131K tokens.

Which is cheaper, Gemini 2.5 Flash or gpt-oss-120b?

Gemini 2.5 Flash costs $0.30 per million input tokens and $2.50 per million output tokens; gpt-oss-120b costs $0.15 and $0.60. Per solved SWE-bench Verified task, Gemini 2.5 Flash costs $0.466 and gpt-oss-120b $0.51.

Which has the bigger context window, Gemini 2.5 Flash or gpt-oss-120b?

Gemini 2.5 Flash, with 1.05M tokens against 131K.

How many benchmarks is the Gemini 2.5 Flash vs gpt-oss-120b comparison based on?

52 benchmarks have a result for both models as of October 21, 2026. Gemini 2.5 Flash's coding index rests on 1 independent benchmark and gpt-oss-120b's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next