Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Command A+ and GPT-5 (medium) are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Command A+ vs GPT-5 (medium)
Updated October 2, 2026. Rank says GPT-5 (medium) is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Decision reading
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead. 0 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 0
- Command A+ only
- 5
- GPT-5 (medium) only
- 0
- Like-for-like categories
- 0 / 8
Estimated: Command A+ and GPT-5 (medium). Conditional ranges do not establish rank confidence.How the comparison works
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
No workload recommendation clears the current evidence threshold.
Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.
Show secondary and unsupported calls
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GPT-5 (medium) is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limitedLong documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documentedChat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-ratesCache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Command A+ does not fit this workload in one request. GPT-5 (medium) does not fit this workload in one request. Command A+ has no published cached-input rate, so cached tokens use its listed input rate. GPT-5 (medium) has no comparable published API token rate.
Confidence: rate-fallbackRepository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Which one for a specific job
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
23.3Command A+35.3GPT-5 (medium)
Directional only · BenchAlign v5.8
GPT-5 (medium) has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
5 Command A+ only
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Coding
Directional only- Command A+
- 23.3
- Estimated · #112/144
- GPT-5 (medium)
- 35.3
- Estimated · #82/144
- Basis
- BenchAlign v5.8 lane · 0 vs 0 public rows
- Reading
- Directional only
Knowledge
Directional only- Command A+
- 27.7
- Estimated · #145/171
- GPT-5 (medium)
- 47.5
- Estimated · #75/171
- Basis
- BenchAlign v5.8 lane · 0 vs 0 public rows
- Reading
- Directional only
Instruction following
Directional only- Command A+
- 89.2
- #20/125
- GPT-5 (medium)
- 84.9
- #37/125
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Directional only
Agentic
Not comparable- Command A+
- 15.9
- Estimated · #102/119
- GPT-5 (medium)
- Not ranked
- Basis
- BenchAlign v5.8 lane · 2 vs 0 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Command A+
- 58.5
- Unranked · 2 rankable rows
- GPT-5 (medium)
- 74.6
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Command A+
- 16.1
- #48/49
- GPT-5 (medium)
- 70.5
- Unranked · 1 rankable row
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Command A+
- Not ranked
- GPT-5 (medium)
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Command A+
- Not ranked
- GPT-5 (medium)
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Command A+ | GPT-5 (medium) | Basis | Reading |
|---|---|---|---|---|
| Coding | 23.3Estimated · #112/144 | 35.3Estimated · #82/144 | Directional onlyBenchAlign v5.8 lane · 0 vs 0 public rows | Directional only |
| Knowledge | 27.7Estimated · #145/171 | 47.5Estimated · #75/171 | Directional onlyBenchAlign v5.8 lane · 0 vs 0 public rows | Directional only |
| Instruction following | 89.2#20/125 | 84.9#37/125 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Agentic | 15.9Estimated · #102/119 | Not ranked | Not comparableBenchAlign v5.8 lane · 2 vs 0 public rows | Not comparable |
| Reasoning | 58.5Unranked · 2 rankable rows | 74.6Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 16.1#48/49 | 70.5Unranked · 1 rankable row | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Bars run 0–100Methodology
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Command A+
- $0.0075
- Fits in one request
- GPT-5 (medium)
- API rate not published
- Fits in one request
GPT-5 (medium) has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Command A+
- $0.155
- Fits in one request
- GPT-5 (medium)
- API rate not published
- Fits in one request
GPT-5 (medium) has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Command A+
- $0.65
- Does not fit in one request
- Cached input priced at the published list-input rate
- GPT-5 (medium)
- API rate not published
- Does not fit in one request
- Cached-input rate unavailable
Command A+ does not fit this workload in one request. GPT-5 (medium) does not fit this workload in one request. Command A+ has no published cached-input rate, so cached tokens use its listed input rate. GPT-5 (medium) has no comparable published API token rate.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationCommand A+GPT-5 (medium)
Context window
Maximum documented context; output-token limits may be lower.
Command A+
128K
GPT-5 (medium)
128K
API model ID
Command A+
Not sourced
GPT-5 (medium)
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Command A+
Not published
GPT-5 (medium)
No comparable hosted API rate
Documented inputs
Command A+
Not sourced
GPT-5 (medium)
Not sourced
Documented outputs
Command A+
Not sourced
GPT-5 (medium)
Not sourced
Provider availability
Command A+
Not sourced
GPT-5 (medium)
Not sourced
Reasoning profile
Command A+
Reasoning
GPT-5 (medium)
Reasoning
Weight access
Command A+
Open Weight
GPT-5 (medium)
Proprietary
License
Command A+
Open Weight
GPT-5 (medium)
Proprietary
Release date
Command A+
2026-05-20
GPT-5 (medium)
2025-08-07
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Both models list 128K.
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Command A+ or GPT-5 (medium)?
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Command A+ or GPT-5 (medium)?
GPT-5 (medium) scores higher for coding on the public lane, 35.3 to 23.3. Command A+ and GPT-5 (medium) are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, Command A+ or GPT-5 (medium)?
GPT-5 (medium) is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Command A+ or GPT-5 (medium)?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, Command A+ or GPT-5 (medium)?
Both models list the same context window, 128K.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence5 rows
Agentic
Multimodal
5 public results · 0 shared
Watch Command A+ vs GPT-5 (medium)
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.
Last updated October 2, 2026